© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 60525
    Prev
    Next
    INDEX
    Explanations

    size and requirements

    np_acts-logits-general · gemini-2.5-flash-lite

    growing or approaching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anting
    0.42
    하였다
    0.42
     作为
    0.41
     혹은
    0.40
    陰
    0.40
    Excuse
    0.40
    অথ
    0.40
    ренко
    0.40
    ']]
    0.39
    あるいは
    0.39
    POSITIVE LOGITS
     it
    0.52
    cology
    0.50
     our
    0.48
     those
    0.46
     abbrevi
    0.45
     very
    0.45
     illegally
    0.45
     brutally
    0.45
     nuestra
    0.45
     bright
    0.44
    Activations Density 0.000%

    No Known Activations